Model save

README.md

@@ -1,6 +1,4 @@
 ---
-language:
-- id
 license: apache-2.0
 base_model: LazarusNLP/IndoNanoT5-base
 tags:
@@ -19,11 +17,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [LazarusNLP/IndoNanoT5-base](https://huggingface.co/LazarusNLP/IndoNanoT5-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4862
-- Rouge1: 0.3867
+- Loss: 0.6973
+- Rouge1: 0.6972
 - Rouge2: 0.0
-- Rougel: 0.3833
-- Rougelsum: 0.386
+- Rougel: 0.6971
+- Rougelsum: 0.6984
 - Gen Len: 1.0
 
 ## Model description
@@ -43,9 +41,9 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
-- train_batch_size: 4
-- eval_batch_size: 8
+- learning_rate: 0.001
+- train_batch_size: 16
+- eval_batch_size: 32
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -53,18 +51,18 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step  | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
-|:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
-| 0.6352        | 1.0   | 3573  | 0.4614          | 0.3871 | 0.0    | 0.3846 | 0.3884    | 1.0     |
-| 0.4361        | 2.0   | 7146  | 0.4357          | 0.3574 | 0.0    | 0.3543 | 0.3544    | 1.0     |
-| 0.3391        | 3.0   | 10719 | 0.4479          | 0.3973 | 0.0    | 0.3975 | 0.4009    | 1.0     |
-| 0.2686        | 4.0   | 14292 | 0.4639          | 0.4113 | 0.0    | 0.4102 | 0.4115    | 1.0     |
-| 0.2221        | 5.0   | 17865 | 0.4862          | 0.3867 | 0.0    | 0.3833 | 0.386     | 1.0     |
+| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
+| 1.21          | 1.0   | 894  | 0.7570          | 0.6899 | 0.0    | 0.6953 | 0.6878    | 1.0     |
+| 0.6826        | 2.0   | 1788 | 0.6250          | 0.6779 | 0.0    | 0.6777 | 0.6768    | 1.0     |
+| 0.4899        | 3.0   | 2682 | 0.5915          | 0.6825 | 0.0    | 0.681  | 0.6837    | 1.0     |
+| 0.3413        | 4.0   | 3576 | 0.6194          | 0.7341 | 0.0    | 0.7341 | 0.7373    | 1.0     |
+| 0.2044        | 5.0   | 4470 | 0.6973          | 0.6972 | 0.0    | 0.6971 | 0.6984    | 1.0     |
 
 
 ### Framework versions
 
 - Transformers 4.40.2
-- Pytorch 2.3.0+cu121
-- Datasets 2.19.1
+- Pytorch 2.3.1+cu121
+- Datasets 2.20.0
 - Tokenizers 0.19.1